Metraipolis › archive › dc_9eb2ee30bc8c

Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings — arXiv:2609.03376

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03376
License (as archived)
CC0-1.0
Archived
2026-10-17T02:03:59.903Z
SHA-256 of the archived text
88a95065f00192044047e3dfa04ee01d8855639b16a0668f25e71459fbffb335
Stable URL of this page
https://metraipolis.com/documento/dc_9eb2ee30bc8c

How to cite

Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings — arXiv:2609.03376 — arXiv (en), https://arxiv.org/abs/2609.03376 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9eb2ee30bc8c (Metraipolis archive dc_9eb2ee30bc8c, sha256 88a95065f00192044047e3dfa04ee01d8855639b16a0668f25e71459fbffb335)
BibTeX
@misc{dc9eb2ee30bc8c,
  title = {Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings — arXiv:2609.03376},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03376},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9eb2ee30bc8c; sha256 88a95065f00192044047e3dfa04ee01d8855639b16a0668f25e71459fbffb335},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03376. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-Augmented Generation (RAG) has made dense retrieval over large document collections a standard building block. Organizations increasingly outsource vector indexes to untrusted clouds, exposing proprietary corpora and user queries. Cryptographic protection is challenging because each query searches corpus-scale state, causing computation, correlated randomness, and communication to grow with the corpus. At million-document scale, a naive secure implementation takes minutes and about 90 GB of communication per query. Even recent optimized systems require 10--22 seconds. We propose Spruce (Scalable Private Outsourced Retrieval Using Compact Embeddings), which co-designs representations with the cryptographic protocol. Spruce learns compact binary codes that preserve candidates for full-precision reranking, replacing corpus-wide embedding scoring with efficient Hamming-distance computation under two-server multi-party computation (MPC). A corpus-calibrated fixed-radius protocol avoids multi-round candidate selection while preserving retrieval quality. Spruce also provides private cluster pruning, which trades minor quality loss for substantially less computation, and a one-core owner-operated dealer that removes cloud OT preprocessing bottlenecks. Across four corpora containing 383K--5.42M documents, Spruce preserves the original search quality with median candidate sets of only 382--1,952. At 10 Gbps inter-server bandwidth, full scans take 0.21--2.97 seconds, $4.8$--$6.7\times$ faster than the closest measured prior work. Private pruning takes 0.06--1.09 seconds, achieves $13.1$--$22.9\times$ speedups, and retains $93.9\%$--$97.3\%$ of full-float NDCG. On the largest corpus, pruning and the dealer jointly improve sustained throughput by $31.5\times$ at 1 Gbps per link.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Information Retrieval (cs.IR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.03376 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T01:28:02.799Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).